Instructions to use PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c

SGLang

How to use PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c with Docker Model Runner:
```
docker model run hf.co/PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c
```

AgenticRL-blackbox-260401_231502_cd7fb81c

This repository contains Hugging Face exports for checkpoints from the Miles/Megatron run 260401_231502_cd7fb81c.

Each checkpoint is uploaded under its own subdirectory to avoid overwriting sharded weight filenames.

Checkpoints

global_step_9/: exported from iter_0000009
global_step_19/: exported from iter_0000019
global_step_29/: exported from iter_0000029
global_step_39/: exported from iter_0000039
global_step_49/: exported from iter_0000049
global_step_59/: exported from iter_0000059
global_step_69/: exported from iter_0000069
global_step_79/: exported from iter_0000079
global_step_89/: exported from iter_0000089
global_step_99/: exported from iter_0000099
global_step_109/: exported from iter_0000109
global_step_119/: exported from iter_0000119
global_step_129/: exported from iter_0000129
global_step_139/: exported from iter_0000139
global_step_149/: exported from iter_0000149
global_step_159/: exported from iter_0000159
global_step_169/: exported from iter_0000169
global_step_179/: exported from iter_0000179

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for PGCodeLLM/AgenticRL-blackbox-260401_231502_cd7fb81c

Base model

Qwen/Qwen3-32B

Finetuned

(514)

this model